Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Xia Li

Xia Li

4 indexed papers

Recent (6 mo)
3
With code
0
Influential cites
0
Benchmarked
0

Publications per year

4
26

Top categories

AI×2Vision×1NLP×1ML×1Quantum Physics×1Crypto×1

Frequent co-authors

Yi Zhang2×
Hongyang Du1×
Yunfei Xie1×
Junjie Ye1×
Jiawei Yang1×
Xiaoyan Cong1×

Research Timeline

2026
Efficient Quantum Fully Homomorphic Encryption

The paper introduces a unified framework for Quantum Fully Homomorphic Encryption (QFHE) that achieves exponential efficiency improvements by integrating a novel modular arithmetic program (MAP) tailored for LWE decryption, the garden-hose model, and measurement-based quantum computation (MBQC).

Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs

The paper proposes Dual-Scale Retentive Dynamics (DSRD), a unified framework that improves representation learning on dynamic graphs by jointly modeling evolving temporal and structural dependencies.

PatchWorld: Gradient-Free Optimization of Executable World Models

PatchWorld introduces a gradient-free framework to create executable Python world models from offline trajectories, achieving high planning scores by inducing symbolic belief-state programs.

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

The paper introduces FuseReg, a method that replaces heuristic feature selection with training over random subsets of encoder layers in representation autoencoders.

Highlighted terms show continued research focus across papers

Papers

cs.CVEmpiricalRecentSep 25, 2026

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

Hongyang Du, Yunfei Xie, Junjie Ye, Jiawei Yang +12 more

The paper introduces FuseReg, a method that replaces heuristic feature selection with training over random subsets of encoder layers in representation autoencoders.

View →
cs.CLcs.AIRecentMay 29, 2026

PatchWorld: Gradient-Free Optimization of Executable World Models

Jiaxin Bai, Yue Guo, Yifei Dong, Jiaxuan Xiong +12 more

PatchWorld introduces a gradient-free framework to create executable Python world models from offline trajectories, achieving high planning scores by inducing symbolic belief-state programs.

View →
cs.LGcs.AIRecentMay 28, 2026

Forget Less, Generalize More: Unifying Temporal and Structural Adaptation for Dynamic Graphs

Qian Chang, Ciprian Doru Giurcaneanu, Runsong Jia, Xia Li +5 more

The paper proposes Dual-Scale Retentive Dynamics (DSRD), a unified framework that improves representation learning on dynamic graphs by jointly modeling evolving temporal and structural dependencies.

View →
quant-phcs.CRApr 26, 2026

Efficient Quantum Fully Homomorphic Encryption

Fengxia Liu, Zixian Gong, Kun Tian, Yi Zhang +2 more

The paper introduces a unified framework for Quantum Fully Homomorphic Encryption (QFHE) that achieves exponential efficiency improvements by integrating a novel modular arithmetic program (MAP) tailo…

View →